Analysis and forecasting of port logistics using TEI@I methodology

Xin TIAN, Liming LIU, K. K. LAI, Shouyang WANG

Research output: Journal PublicationsJournal Article (refereed)peer-review

12 Citations (Scopus)


This paper presents an integrated forecasting model based on the TEI@I methodology for forecasting demand for port logistics services - specifically, port container throughput. The model analyzes port logistics time series data and other information in several steps. In the first step, several econometric models are built to forecast the linear segment of port logistics time series. In the second step, a radial basis function neural network is developed to predict the nonlinear segment of the time series. In the third step, the event-study method and expert system techniques are applied to evaluate the effects of economic and other events that may impact demand for port logistics. In the final step, synthetic forecasting results are obtained, based on the integration of predictions from the above three steps. For an illustration, Hong Kong port's container throughput series is used as a case study. The empirical results show the effectiveness of the TEI@I integrated model for port logistics forecasting.
Original languageEnglish
Pages (from-to)685-702
Number of pages18
JournalTransportation Planning and Technology
Issue number8
Early online date30 Oct 2013
Publication statusPublished - 2013


  • TEI@I methodology
  • artificial neural network
  • container throughput
  • econometric models
  • forecasting
  • port logistics


Dive into the research topics of 'Analysis and forecasting of port logistics using TEI@I methodology'. Together they form a unique fingerprint.

Cite this